Skip to content

sferarc/pgbeam

v1.0.0Apache-2.0

Safe Postgres access for AI agents. Scoped credentials, read-only by default, table and column allowlists, PII masking, query budgets, a kill-switch, and a full audit trail, all enforced in the Postgres wire protocol.

pgbeam-audit

Investigate and export what an agent actually did against Postgres using PgBeam's audit trail. Use this when you need to answer "what did this agent run", show a reviewer or auditor that a credential was held to its policy, export statement history to CSV or a SIEM, verify the tamper-evident audit chain, or turn recorded traffic into a tighter policy. For creating credentials use pgbeam-connect, for authoring the policy itself use pgbeam-policy.

Read SKILL.md at the source

Pinned to revision 376f50899432, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.